freewheelin
commited on
Commit
•
2caf118
1
Parent(s):
6357bc9
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,18 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- ko
|
4 |
+
- en
|
5 |
+
license: mit
|
6 |
+
---
|
7 |
+
|
8 |
+
# Model Card for free-llama-dpo-v0.2
|
9 |
+
|
10 |
+
## Developed by : [Freewheelin](https://freewheelin-recruit.oopy.io/) AI Technical Team
|
11 |
+
|
12 |
+
## Hardware and Software
|
13 |
+
|
14 |
+
* **Training Factors**: We fine-tuned this model using the [HuggingFace TRL Trainer](https://huggingface.co/docs/trl/trainer)
|
15 |
+
|
16 |
+
## Method
|
17 |
+
- This model was trained using the learning method introduced in the [SOLAR paper](https://arxiv.org/pdf/2312.15166.pdf).
|
18 |
+
|